Connectionists: CFP: MultiClinSum-2 - Multilingual Clinical Summarization Shared Task at CLEF 2026

Wed Feb 25 06:52:10 EST 2026

CFP MultiClinSum-2 (CLEF/BioASQ 2026)

 Multilingual Clinical Text Summarization Shared Task (2nd edition)

https://temu.bsc.es/multiclinsum2/

In light of recent technological advances in NLP and LLMs, there is a
pressing need to evaluate and benchmark the effectiveness of clinical
summarization for case reports written in different languages.
MultiClinSum-2 addresses this need by focusing on the automatic
summarization of full clinical case reports across 15 languages: English,
French, Spanish, Portuguese, Italian, Russian, Catalan, Norwegian, Danish,
Romanian, German, Greek, Dutch, Czech, and Swedish. Since clinical case
reports share structural and content similarities with electronic medical
records, particularly discharge summaries, insights derived from
MultiClinSum-2 may have practical relevance for clinical text analysis and
various healthcare applications.

The task dataset combines two complementary sources: a carefully selected
collection of case reports from PubMed in English, Spanish, French, and
Portuguese, accompanied by author-written summaries ensuring clinical
accuracy; and a large-scale component derived from the PMC-Patients subset,
where summaries were extracted from specific sections of the original
abstracts. All full case - summary pairs were translated into all remaining
15 supported languages of the task.

Key Information:

   -

   Website: <https://temu.bsc.es/multiclinsum>
   https://temu.bsc.es/multiclinsum2/
   -

   BioASQ Workshop 2026: http://bioasq.org/
   -

   CLEF 2026 Registration: https://clef-labs-registration.dipintra.it/
   -

   Sample Dataset: https://zenodo.org/records/18663291

Motivation:

Clinical documentation continues to grow at an unprecedented rate across
healthcare systems worldwide, encompassing diverse formats such as
electronic health records and specialized publications like clinical case
reports. This content exists in numerous languages beyond English,
reflecting the global nature of medical practice. The extensive length of
many clinical reports presents a significant barrier for healthcare
professionals and biomedical researchers who must efficiently extract
essential clinical information from large volumes of clinical data.

Recent advances in large language models (LLMs) and agentic systems, have
demonstrated substantial potential for automated text summarization,
offering the capability to create comprehensive clinical narratives into
concise summaries that retain critical diagnostic, relevant clinical
details, and underlying medical insights, while dramatically reducing
document length. This creates an urgent need to evaluate and compare the
performance of clinical summarisation systems in multiple languages.

Use Cases and Application Scenarios

Automatic clinical text summarization supports a wide range of healthcare
applications:

   -

   Clinical Decision Support: Summarization condenses electronic health
   records (EHRs) into key events, diagnoses, medications, and outcomes,
   aiding timely and informed decisions.
   -

   Patient Discharge Summaries: Automatically generate readable, concise
   summaries from detailed clinical notes, enhancing continuity of care and
   patient understanding.
   -

   Medical Literature Review: Summarize key findings, methodologies, and
   outcomes from scientific articles to facilitate rapid literature reviews.
   -

   Multilingual Clinical Communication: Summarization systems, combined
   with translation, enable understanding across language barriers by
   distilling essential content from foreign-language reports.
   -

   Telemedicine & Remote Consultations: Summarized patient data supports
   fast review and focused diagnostics in remote care settings.
   -

   Clinical Trial Screening: Summarized profiles can accelerate eligibility
   assessment by highlighting key inclusion/exclusion criteria.
   -

   Medical Coding and Billing: Summarization helps highlight billable
   actions, diagnoses, and procedures to streamline medical coding workflows.
   -

   Patient-Facing Summaries: Summarization tools can generate simplified or
   lay-language versions of complex medical content to improve patient
   engagement and health literacy.

Evaluation

The task features one independent sub-track for each of the 15 languages.
Automatically-generated summaries will be compared against gold standard
summaries using Rouge-2 and BERTScore, in addition to Multi-Agent System
(MAS) as judge strategies that will be also explored for assessing
information loss and retention. Each language sub-track will be evaluated
independently. Participants are encouraged to explore both monolingual and
multilingual approaches and may participate in as many language subtracks
as desired.

Schedule

   -

   Sample set release: February 16th, 2026
   -

   Training set release: March 5th, 2026
   -

   Test full cases set release: April 27th, 2026
   -

   Participants Test Predictions Deadline: May 8th 15:00 CET, 2026
   -

   Participant Evaluation Result Release: May 15th, 2026
   -

   Submission of Participant Papers Deadline: May 28th at 15:00 CET (see
   instructions <https://clef2026.clef-initiative.eu/calls/submitting/> for
   CLEF Lab Working Notes)
   -

   Notification of Acceptance of Participant Papers: June 30th, 2026
   -

   Submission of Camera-ready Participant Papers Deadline: July 6th, 2026
   -

   BioASQ Workshop at CLEF 2026: September 21-24, 2026 Jena, Germany.

Publications & Conference

Following previous BioASQ/CLEF efforts, participating teams will be invited
to contribute a short system description paper for the CLEF 2026
proceedings and to give a brief presentation of their approach at the
BioASQ workshop during the CLEF 2026 conference, hosted by
Friedrich-Schiller-Universität Jena, Germany from September 21-24, 2026.

Organizers

   -

   Miguel Rodríguez-Ortega <miguel.rod.bsc at gmail.com>, Barcelona
   Supercomputing Center (BSC), Spain.
   -

   Eduard Rodríguez-López <edu4bsc at gmail.com>, Barcelona Supercomputing
   Center (BSC), Spain.
   -

   Salvador Lima-López <salvador.limalopez at gmail.com>, Barcelona
   Supercomputing Center (BSC), Spain.
   -

   Audrey Mash, Barcelona Supercomputing Center (BSC), Spain.
   -

   Maite Melero Nogues, Barcelona Supercomputing Center (BSC), Spain.
   -

   Martin Krallinger <Krallinger.Martin at gmail.com>, Barcelona
   Supercomputing Center (BSC), Spain.

-- 
--
*Miguel Rodríguez Ortega*

*Research Engineer*
NLP for Biomedical Information Analysis - Life Sciences
*Barcelona Supercomputing Center – Centro Nacional de Supercomputación*
miguel.rod.bsc at gmail.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20260225/e32cfbf2/attachment.html>